Bladder volume prediction method based on deep learning

Abstract

The invention belongs to the technical field of medical image processing, and particularly relates to a bladder volume prediction method based on deep learning, and the method comprises the steps: building a bladder volume and risk level multi-task prediction model, training an input image and text information, and carrying out the prediction of the bladder volume and the risk level through the trained model. According to the method, an efficient deep learning network architecture is designed by fusing image and text multi-modal information, and the accuracy and robustness of bladder volume prediction and risk level classification are remarkably improved; the image information extraction module is combined with an LCIA attention mechanism to effectively capture details of local areas and global features; the text information embedding module strengthens the expression ability of non-image information through low-dimensional expression; and the RFEA multi-modal feature fusion module dynamically adjusts the importance of multi-modal data, so that the image and text features can act synergistically, and the overall prediction performance is improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of medical image processing, and in particular relates to a bladder volume prediction method based on deep learning. Background Art

[0002] Bladder volume measurement is an important basis for the diagnosis and treatment of urinary system diseases and is widely used in clinical scenarios such as urinary retention, bladder dysfunction, prostate disease and postoperative rehabilitation assessment. Traditional measurement methods mainly include catheterization and ultrasound scanning. Catheterization directly empties the bladder and measures urine volume by inserting a catheter. Although it has high accuracy, it is highly invasive and can easily cause patient discomfort and infection risks. Ultrasound scanning has become the mainstream method due to its non-invasive, fast and real-time characteristics, but its accuracy is significantly affected by the operator's experience and image quality, especially when there are anatomical variations, body shape differences or image blur, which may lead to large errors. With the development of medical technology, the demand for automation and intelligence has become increasingly prominent. The measurement method based on traditional methods is difficult to meet the needs of fast, accurate and large-scale diagnosis and treatment. In this context, deep learning technology, due to its powerful data-driven capabilities and feature extraction advantages, provides an innovative direction for bladder volume measurement. The deep learning algorithm can automatically extract the bladder edge and calculate the bladder capacity from the ultrasound image, getting rid of the dependence on manual experience, which not only improves the efficiency and accuracy of the measurement, but also can handle blurred images and multimodal data in complex scenarios. In addition, multimodal learning further enhances the diagnostic ability and generalization of the model by combining information such as the patient's age, gender, and medical history. Therefore, the application of deep learning in bladder volume measurement not only makes up for the shortcomings of traditional methods, but also provides important support for the research and development and promotion of intelligent medical equipment, showing significant clinical and application value.

[0003] Therefore, the application of deep learning in bladder volume measurement not only makes up for the shortcomings of traditional methods, but also provides important support for the development and promotion of intelligent medical equipment, showing significant clinical and application value. However, traditional methods have poor adaptability in complex scenarios and are highly dependent on operating experience, making it difficult to meet the needs of modern medicine for high efficiency and accurate diagnosis. Summary of the invention

[0004] In order to solve the above technical problems, the present invention provides a bladder volume prediction method based on deep learning, comprising:

[0005] Establish a multi-task prediction model for bladder volume and risk level, train the input image and text information, and use the trained model to predict bladder volume and risk level;

[0006] The bladder volume prediction model includes: an image information extraction module, an LCIA attention mechanism module, a text information embedding module, and an RFEA multimodal feature fusion module;

[0007] The training of the bladder volume prediction model comprises:

[0008] S1: Apply feature selection algorithms to automatically select the most relevant feature subsets from multimodal datasets to improve the model prediction performance and training efficiency of multimodal data;

[0009] S2: The image in the most relevant feature subset is input into the image information extraction module and the LCIA attention mechanism module for processing in sequence to obtain image feature information;

[0010] The image information extraction module obtains basic image features and provides initial information input for subsequent modules;

[0011] The LCIA attention mechanism module combines the local area features and channel features in the basic features of the image to extract effective information more accurately;

[0012] S3: The text information in the most relevant feature subset is transformed into low-dimensional text information through the text information embedding module to obtain text feature information, so that the text information can be processed in the neural network and work together with the image features, thereby improving the accuracy of the model in bladder volume prediction and risk level classification;

[0013] S4: Through the RFEA multimodal feature fusion module, the image feature information and text feature information are weighted and fused to improve the performance of the model;

[0014] S5: Design a dynamic multi-task loss function to ensure that the model's attention is automatically balanced between the loss values ​​of different tasks, so that the model can better cope with volume scale differences and category imbalance problems, improving overall performance and robustness.

[0015] Beneficial effects of the present invention:

[0016] By fusing image and text multimodal information, the present invention designs an efficient deep learning network architecture, which significantly improves the accuracy and robustness of bladder volume prediction and risk level classification; the image information extraction module combines the LCIA attention mechanism to effectively capture the details of local areas and global features; the text information embedding module enhances the expression ability of non-image information through low-dimensional representation; the RFEA multimodal feature fusion module dynamically adjusts the importance of multimodal data so that image and text features can work together to improve the overall prediction performance; the dynamic multi-task loss function adaptively balances the losses of bladder volume prediction and risk level classification, significantly solves the problems of volume scale difference and category imbalance, and enhances the adaptability of the model to practical applications.

[0017] In addition, the present invention introduces a multimodal feature optimization selection method (MMFS), which improves data analysis efficiency and prediction ability by automatically screening the most relevant features. Compared with traditional methods, the present invention can more comprehensively capture bladder-related lesion information, while optimizing computational efficiency and reducing training time. In actual clinical applications, the present invention provides more accurate support for bladder function assessment, disease risk prediction, and treatment plan formulation, and opens up a new way to improve the intelligence level and diagnostic quality of medical image analysis. It has important scientific research value and broad application prospects. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 It is a schematic diagram of the process of the present invention. DETAILED DESCRIPTION

[0019] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0020] A bladder volume prediction method based on deep learning, comprising:

[0021] Establish a multi-task prediction model for bladder volume and risk level, train the input image and text information, and use the trained model to predict bladder volume and risk level;

[0022] The bladder volume prediction model includes: an image information extraction module, an LCIA attention mechanism module, a text information embedding module, and an RFEA multimodal feature fusion module;

[0023] The training of the bladder volume prediction model comprises:

[0024] S1: Applying a feature selection algorithm to automatically select the most relevant feature subset from a multimodal data set to improve the model prediction performance and training efficiency of the multimodal data; the multimodal data set consists of bladder data;

[0025] S2: The image in the most relevant feature subset is input into the image information extraction module and the LCIA attention mechanism module for processing in sequence to obtain image feature information;

[0026] The image information extraction module obtains basic image features and provides initial information input for subsequent modules;

[0027] The LCIA attention mechanism module combines the local area features and channel features in the basic features of the image to extract effective information more accurately;

[0028] S3: The text information in the most relevant feature subset is transformed into low-dimensional text information through the text information embedding module to obtain text feature information, so that the text information can be processed in the neural network and work together with the image features, thereby improving the accuracy of the model in bladder volume prediction and risk level classification;

[0029] S4: Through the RFEA multimodal feature fusion module, the image feature information and text feature information are weighted and fused to improve the performance of the model;

[0030] S5: Design a dynamic multi-task loss function to ensure that the model's attention is automatically balanced between the loss values ​​of different tasks, so that the model can better cope with volume scale differences and category imbalance problems, improving overall performance and robustness.

[0031] Step 1: Before model training, the multimodal feature selection method (MMFS) is first applied to automatically screen the input multimodal data. By analyzing the correlation between images, texts, and other patient information, the most predictive features for bladder volume prediction and risk level classification tasks are selected. This can reduce the interference of redundant features on model training, improve computational efficiency, and enhance the final prediction performance.

[0032] Step 2: Input the image information into the image feature extraction module. The core task of the image feature extraction module is to extract deep feature information from the bladder ultrasound image to provide support for subsequent bladder volume prediction and risk level classification. Through a multi-layer convolutional neural network (CNN), the image feature extraction module can gradually extract key information from the input image and form a feature vector that can effectively represent the image content.

[0033] Step 2.1: Input the output of the image information extraction module to the LCIA attention mechanism module The core task of the LCIA attention mechanism module is to improve the expressiveness of image features. This module combines the local area features and channel features of the image, and through weighted operations, enables the model to pay more attention to the key parts related to the task.

[0034] Step 3: At the same time, the corresponding text information is input into the text information embedding module. The main function of the text information embedding module is to convert the patient's unstructured text information (such as gender, age, medical history, region, etc.) into a low-dimensional vector representation so that it can be fused and processed together with the image features in the deep learning model. In this way, the model can simultaneously utilize the features of image and text data, comprehensively consider the multi-dimensional background information of the patient, thereby improving the accuracy of bladder volume prediction and the effect of risk level classification.

[0035] The text information is converted into a low-dimensional vector representation through the text information embedding module, including:

[0036]

[0037] Among them, V(t i ) represents the low-dimensional vector representation obtained by transformation, V(w j ) represents the word embedding vector, w j Represents the words in the symptom text description, n i Represents text t i The number of words in V(t i ) represents the text t i The vector representation of .

[0038] Step 4: The output obtained by the text information embedding module and the output obtained in step 2.1 are simultaneously input into the RFEA multimodal feature fusion module. The RFEA multimodal feature fusion module is responsible for weighted fusion of features from the image extraction module and the text information embedding module. The fused features are processed by two task branches: the bladder volume prediction branch uses a fully connected layer to regress the output volume value; the risk level prediction branch uses a fully connected layer and a softmax activation function to achieve classification. Through this module, the model can comprehensively utilize information from multiple data sources to improve the prediction performance of bladder volume and risk level. Weighted fusion between different modalities can help the model better handle the complementarity of image and text information and provide more comprehensive diagnostic support.

[0039] Step 5: Design a dynamic multi-task loss function to balance the losses of different tasks. For the bladder volume prediction and risk level classification tasks, the loss function can automatically adjust the focus according to the nature and objectives of the task to ensure that the model can achieve the best performance when dealing with volume scale differences and category imbalance problems. Through multi-task learning, the model can not only complete the prediction of multiple tasks, but also share useful knowledge between tasks, thereby improving overall performance and robustness. The dynamic multi-task loss function is expressed as:

[0040] L all =λ1L v+λ2L r

[0041] L v =αNAME+(1-α)MSE

[0042]

[0043] Among them, L all represents the dynamic multi-task loss function, L v represents the bladder volume prediction loss function, L r represents the risk level classification loss function, λ1 and λ2 represent the dynamic weights of bladder volume prediction and risk level classification prediction, α represents the weight for controlling the mean absolute error and mean square error loss, NAME represents the standardized mean absolute error, and MSE represents the mean square error; y i represents the true volume, y' i represents the prediction volume, ∈ represents a small constant to prevent the denominator from being zero, N represents the number of samples when calculating the loss, and C represents the number of categories; p ic represents the predicted probability that the i-th sample belongs to the c-th class, α c represents the class weight, and γ represents the focusing factor that reduces the loss of easy-to-classify samples.

[0044] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A bladder volume prediction method based on deep learning, characterized in that: include: Establish a multi-task prediction model for bladder volume and risk level, train the input image and text information, and use the trained model to predict bladder volume and risk level; The multi-task prediction model of bladder volume and risk level includes: an image information extraction module, an LCIA attention mechanism module, a text information embedding module, and an RFEA multimodal feature fusion module; The training of the bladder volume prediction model comprises: S1: Apply multimodal feature optimization selection methods to automatically select the most relevant feature subsets from multimodal datasets to improve the model prediction performance and training efficiency of multimodal data; S2: The image in the most relevant feature subset is input into the image information extraction module and the LCIA attention mechanism module for processing in sequence to obtain image feature information; The image information extraction module obtains basic image features and provides initial information input for subsequent modules; The LCIA attention mechanism module combines the local area features and channel features in the basic features of the image to extract effective information more accurately; S3: The text information in the most relevant feature subset is transformed into low-dimensional text information through the text information embedding module to obtain text feature information, so that the text information can be processed in the neural network and work together with the image features, thereby improving the accuracy of the model in bladder volume prediction and risk level classification; S4: Through the RFEA multimodal feature fusion module, the image feature information and text feature information are weighted and fused to complete the bladder volume and risk level prediction; S5: Design a dynamic multi-task loss function to ensure that the model's attention is automatically balanced between the loss values ​​of different tasks, so that the model can better cope with volume scale differences and category imbalance problems, improving overall performance and robustness.

2. The method for predicting bladder volume based on deep learning according to claim 1, characterized in that: Apply multimodal feature optimization selection methods to automatically select the most relevant feature subsets from multimodal datasets to improve the model prediction performance and training efficiency of multimodal data, including: Initializing feature subsets: randomly selecting multiple feature subsets from a multimodal dataset based on the dimensions of the data and the types of features to ensure that different feature combinations are covered; the multimodal dataset includes: images, text, and clinical data; Evaluate and select the optimal subset: Use the mean square error in the regression task and the accuracy in the classification task as evaluation criteria to evaluate the performance of each feature subset and select the feature subset with the best fitness value. These subsets will serve as the basis for subsequent optimization. Optimize feature sets: Optimize feature subsets through feature combination and redundancy removal. The optimized feature subsets will focus more on the core information of the task, improving the prediction ability and computing efficiency of the model. Iterative optimization: Repeat the above process and gradually optimize the feature subset through multiple iterations. After each iteration, adjust the feature subset according to the new evaluation results and fitness until the predetermined performance target or the maximum number of iterations is reached.

3. The method for predicting bladder volume based on deep learning according to claim 1, characterized in that: The image information extraction module consists of five cascaded convolutional layers, which extracts and refines features layer by layer, gradually transforms low-level edge and texture information into high-level global semantic features, and obtains basic image features.

4. The method for predicting bladder volume based on deep learning according to claim 1, characterized in that: The LCIA attention mechanism module combines the local area features and channel features in the basic features of the image to more accurately extract effective information, including: Local area attention calculation: Divide the basic features of the image into multiple areas to obtain local area features, and weight the local area features by dynamically generating convolution kernels to enhance the feature expression ability of key areas; Channel attention calculation: Use global pooling and fully connected networks to weight each channel of the basic features of the image, generate the weight of each channel, and highlight the channel features that contribute to the task; Region and channel interaction: Combine local region attention and channel attention to generate joint weights to strengthen multi-dimensional feature expression and obtain the final image feature information.

5. The method for predicting bladder volume based on deep learning according to claim 1, characterized in that: The text information in the most relevant feature subset is transformed into a low-dimensional form through the text information embedding module to obtain text feature information, including: Among them, V(t i ) represents the low-dimensional vector representation obtained by transformation, V(w j ) represents the word embedding vector, w j Represents the words in the symptom text description, n i Represents text t i The number of words in V(t i ) represents the text t i The vector representation of .

6. The method for predicting bladder volume based on deep learning according to claim 1, characterized in that: Through the RFEA multimodal feature fusion module, the image feature information and text feature information are weighted and fused to complete the bladder volume and risk level prediction, including: Image and text information stitching: stitch the image feature information and text feature information together to obtain a joint feature vector. The stitched features contain global information from the image and text, providing a basis for subsequent correlation analysis. Correlation analysis: The joint feature vector is input into the fully connected layer for processing, and a correlation weight matrix is ​​calculated to represent the correlation between the image and text information, and to provide a weighted basis for subsequent feature fusion; Multimodal information fusion: weighted fusion of image feature information and text feature information through the correlation weight matrix to ensure that they are appropriately combined according to their importance in specific tasks; The fused features are processed by two task branches: the bladder volume prediction branch uses a fully connected layer to regress and output the volume value; the risk level prediction branch implements classification through a fully connected layer and a softmax activation function.

7. The method for predicting bladder volume based on deep learning according to claim 1, characterized in that: The dynamic multi-task loss function, include: L all =λ1L v +λ2L r L v =αNAME+(1-α)MSE Among them, L all represents the dynamic multi-task loss function, L v represents the bladder volume prediction loss function, L r represents the risk level classification loss function, λ1 and λ2 represent the dynamic weights of bladder volume prediction and risk level classification prediction, α represents the weight for controlling the mean absolute error and mean square error loss, NAME represents the standardized mean absolute error, and MSE represents the mean square error; y i represents the true volume, y' i represents the prediction volume, ∈ represents a small constant to prevent the denominator from being zero, N represents the number of samples when calculating the loss, and C represents the number of categories; p ic represents the predicted probability that the i-th sample belongs to the c-th class, α c represents the class weight, and γ represents the focusing factor that reduces the loss of easy-to-classify samples.

Images